US20090306804A1 - Method for prognostic maintenance in semiconductor manufacturing equipments - Google Patents
Method for prognostic maintenance in semiconductor manufacturing equipments Download PDFInfo
- Publication number
- US20090306804A1 US20090306804A1 US12/243,370 US24337008A US2009306804A1 US 20090306804 A1 US20090306804 A1 US 20090306804A1 US 24337008 A US24337008 A US 24337008A US 2009306804 A1 US2009306804 A1 US 2009306804A1
- Authority
- US
- United States
- Prior art keywords
- health
- semiconductor manufacturing
- raw data
- classification
- maintenance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0224—Process history based detection method, e.g. whereby history implies the availability of large amounts of data
- G05B23/024—Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
- G05B23/0275—Fault isolation and identification, e.g. classify fault; estimate cause or root of failure
- G05B23/0281—Quantitative, e.g. mathematical distance; Clustering; Neural networks; Statistical analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
Definitions
- the present invention is related to a prognostic method; in particular, to a method for prognostic maintenance in semiconductor manufacturing equipments, which performs statistic analyses on significantly massive and complicated raw data outputted by semiconductor equipments, allowing in-situ engineers to predict the health level for prognostic repairs and maintenance on semiconductor equipments.
- TBM Time-Based Preventive Maintenance
- CBM Condition-Based Maintenance
- FDC Fault Detection and Classification
- a method is often used in the field of semiconductor for defect inspection parameter analysis (refer to FIG. 2 ), which can be used to analyze a plurality of lots of products.
- Each lot of products respectively has a lot number and is fabricated by means of a plurality of machineries; wherein one or more wafers in each lot of products pass through at least one defect inspection of product to generate a defect inspection parameter, and engineers determine where the problem is located in such a process chain which leads to undesirable wafer yield drop based on the information presented by these parameters.
- the solution provided by the above-said patent is excessively sophisticated, and engineers are required to set many rules to facilitate defect inspection analyses, as a result, it consumes too much time on rule building, leading to poor efficiency in resource application and less preferable practical usability.
- the major objective of the present invention is to provide a method for prognostic maintenance in semiconductor manufacturing equipments, which generates a health report by processing check data provided by the semiconductor equipments, providing in-situ engineers with useful information for prognostic repairs and maintenance, allowing the prevention of failure occurrence in the semiconductor equipments and accordingly improve wafer yield.
- the present invention provides a method for prognostic maintenance in semiconductor manufacturing equipments, comprising the following steps: collecting a plurality of raw data and preprocessing the plurality of collected raw data; then performing classification through a statistic classification model on the plurality of preprocessed raw data to generate a plurality of health indices; performing classification on the plurality of generated health indices by a prescribed classification method to generate a plurality of health information; next, using a regression analysis method to process the plurality of health information to generate a plurality of health reports; finally, actively performing repairs and maintenance by in-situ engineers based on the plurality of generated health reports.
- FIG. 1 is a flowchart of a conventional defect inspection analysis.
- FIG. 2 is a flowchart of a conventional defect inspection parameter analysis method.
- FIG. 3 is a flowchart of the method for prognostic maintenance in semiconductor manufacturing equipments according to the present invention.
- FIG. 4 is a flowchart of the statistic classification model according to the present invention.
- FIG. 5 is a flowchart of the prescribed classification method according to the present invention.
- the present invention proposes a method for prognostic maintenance in semiconductor manufacturing equipments, and the method for prognostic maintenance in semiconductor manufacturing equipments comprising the following steps:
- S 100 collecting a plurality of raw data, and performing preprocesses on the plurality of raw data;
- S 104 performing classification on the plurality of health indices by a prescribed classification method so as to generate a plurality of health information
- FDC Fault Detection and Classification
- preprocess the plurality of raw data which is directed to filter out meaningless null variation values existing in the plurality of raw data, and to generate detection values of normal pattern; and the plurality of raw data further consist of a plurality of historic data and a plurality of newly added data, in which the plurality of historic data indicate the data outputted by the semiconductor equipments under healthy condition in the past, and the plurality of newly added data represent the data outputted by the semiconductor equipment under unknown condition at current time.
- a statistic classification model to process the plurality of preprocessed raw data, which is simply the plurality of raw data after the said preprocess, so as to generate a plurality of health indices
- the statistic classification model refers to the Neural Network Model (NN Model)
- the steps taken in such a statistic classification model comprise (also refer to FIG. 4 ):
- a 100 simplifying the plurality of historic data; that is, performing classification on the plurality of historic data by a neural network classifier, acquiring a plurality of historic neural points;
- a 102 processing the plurality of historic neural points, so as to generate a distribution configuration of the plurality of historic neural points according to the plurality of historic neural points, thus acquiring an elliptic distribution configuration of the plurality of historic neural points.
- B 100 simplifying the plurality of newly added data; that is, performing classification on the plurality of newly added data by the neural network classifier, acquiring a plurality of newly added neural points;
- B 102 processing the plurality of newly added neural points, so as to generate a distribution configuration of the plurality of newly added neural points according to the plurality of newly added neural points, and building the distribution configuration of the plurality of newly added neural points within the above-said elliptic distribution configuration.
- C 100 comparing the plurality of historic neural points with the plurality of newly added neural points based on the elliptic distribution configuration, thus generating a plurality of comparison values
- C 102 conjunctively processing the plurality of comparison values to generate a plurality of health indices.
- the prescribed classification method is essentially the Principal Component Analysis (PCA), and the steps taken in the prescribed classification method comprise (also refer to FIG. 5 ):
- PLS-DA Partial Least Squares Discriminated Analysis
- the plurality of health reports are provided to in-situ engineers for assisting in-situ engineers in appreciating the health condition of the semiconductor equipments beforehand, such that in-situ engineers are capable of actively performing related repairs and maintenance thereon.
- the method of the present invention has the following advantages:
- the method of the present invention uses simple classification operations, and data after such operation processes can provide in-situ engineers with information concerning health level of the semiconductor equipments;
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Automation & Control Theory (AREA)
- Human Resources & Organizations (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Algebra (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Probability & Statistics with Applications (AREA)
- Pure & Applied Mathematics (AREA)
- General Factory Administration (AREA)
- Testing Or Measuring Of Semiconductors Or The Like (AREA)
Abstract
Description
- 1. Field of the Invention
- The present invention is related to a prognostic method; in particular, to a method for prognostic maintenance in semiconductor manufacturing equipments, which performs statistic analyses on significantly massive and complicated raw data outputted by semiconductor equipments, allowing in-situ engineers to predict the health level for prognostic repairs and maintenance on semiconductor equipments.
- 2. Description of Related Art
- As semiconductor manufacturing technologies evolve, the surface area of integrated circuit has been largely reduced, which means small or minor defects generated during semiconductor processes may turn out to be critical factors for integrated circuit quality. Therein, the generation of defects may be caused by many potential problems, and one of these problems may be the health level of aging semiconductor equipments, which causes reduction in wafer yield. Therefore, four methods are commonly applied on current semiconductor equipments for repairs and maintenance so as to increase wafer yield:
- 1. Breakdown Maintenance (BDM)
- This belongs to unplanned equipment repair; that is, engineers perform repairs and maintenance upon the occurrence of damage, breakdown, or failure in the semiconductor equipments.
- 2. Usage-Based Preventive Maintenance (UBM)
- According to the times of usages in the semiconductor equipments, engineers perform repairs and maintenance thereon when a predetermined usage number is reached.
- 3. Time-Based Preventive Maintenance (TBM)
- According to the duration of usages in the semiconductor equipments, engineers perform repairs and maintenance thereon when a predetermined duration of usage time is reached.
- 4. Condition-Based Maintenance (CBM)
- It monitors the semiconductor equipments and collects monitor data, and then engineers determine whether it is required to perform repairs and maintenance based on the collected monitor data.
- Nevertheless, the above-mentioned approaches of quantity-based maintenance as well as time-based maintenance can not prevent occurrence of failure in the semiconductor equipments beforehand, and even by means of the methods such as the said CBM, regarding the collected monitor data, there is currently still no effective methodology to predetermine the health condition of the semiconductor equipments at an early stage, so as to let engineers be able to perform repairs and maintenance on the semiconductor equipments before the problems therein generate undesirable impact on the wafer yield.
- Presently, in the field of semiconductor, engineers use the Fault Detection and Classification (FDC) system to analyze the output data of the semiconductor equipments in order to be aware of the reasons causing wafer defects, so as to enabling appropriate adjustment on the semiconductor equipments by engineers, facilitating trouble shooting procedures and wafer yield enhancement. Initially, the FDC system is used to perform defect inspections, and presents the inspection result in a trend chart; then, engineers observe the variation in the generated trend chart for making decisions according to professional experiences in engineers themselves, so as to locate the causes of such defects (as the flowchart shown in
FIG. 1 ); wherein the data provided by the semiconductor equipments is complicated and massive, thus the trend chart need to display a huge amount of information, and engineers have to spend much time on viewing the changes in the generated trend chart, thereby causing difficulties in problem analysis and tracking for engineers, and less able to control the health level of various semiconductor equipments, which accordingly leading to poor performance on semiconductor equipment management, thus unnecessarily wastes plenty of extra resources on problem finding yet with end results of incapability of wafer yield enhancement. - Presently, for example, a method is often used in the field of semiconductor for defect inspection parameter analysis (refer to
FIG. 2 ), which can be used to analyze a plurality of lots of products. Each lot of products respectively has a lot number and is fabricated by means of a plurality of machineries; wherein one or more wafers in each lot of products pass through at least one defect inspection of product to generate a defect inspection parameter, and engineers determine where the problem is located in such a process chain which leads to undesirable wafer yield drop based on the information presented by these parameters. However, the solution provided by the above-said patent is excessively sophisticated, and engineers are required to set many rules to facilitate defect inspection analyses, as a result, it consumes too much time on rule building, leading to poor efficiency in resource application and less preferable practical usability. - As such, the inventors of the present invention have considered the aforementioned improvable defects and herein proposed the present invention with reasonable design and effectiveness in resolving the said drawbacks.
- The major objective of the present invention is to provide a method for prognostic maintenance in semiconductor manufacturing equipments, which generates a health report by processing check data provided by the semiconductor equipments, providing in-situ engineers with useful information for prognostic repairs and maintenance, allowing the prevention of failure occurrence in the semiconductor equipments and accordingly improve wafer yield.
- To achieve the above-mentioned objective, the present invention provides a method for prognostic maintenance in semiconductor manufacturing equipments, comprising the following steps: collecting a plurality of raw data and preprocessing the plurality of collected raw data; then performing classification through a statistic classification model on the plurality of preprocessed raw data to generate a plurality of health indices; performing classification on the plurality of generated health indices by a prescribed classification method to generate a plurality of health information; next, using a regression analysis method to process the plurality of health information to generate a plurality of health reports; finally, actively performing repairs and maintenance by in-situ engineers based on the plurality of generated health reports.
- The present invention provides the following beneficial effects:
- 1. by using the method of the present invention, it is possible to lessen the massive raw data, allowing for the reduction of system cost and system complexity;
- 2. straight-forward processes facilitate simplification of complicated raw data analyses;
- 3. by using the method of the present invention, it is possible to predict the health level in the semiconductor equipments, enabling active repairs and maintenance of the semiconductor equipments by in-situ engineers;
- 4. performance of semiconductor equipment control and management can be improved, save much analysis time and manpower;
- 5. before occurrences of failure or breakdown in the semiconductor equipments, it is possible to notify in-situ engineers to perform repairs or maintenance beforehand, so as to extend lifespan of the semiconductor equipments and provide enhanced wafer yield.
- For further understanding the characteristics and technical contents of the present invention, references are made to the detailed descriptions and appended drawing of the present invention; however, the appended drawings are simply for the purposes of reference and illustration, rather than being used to limit the scope of present invention thereto.
-
FIG. 1 is a flowchart of a conventional defect inspection analysis. -
FIG. 2 is a flowchart of a conventional defect inspection parameter analysis method. -
FIG. 3 is a flowchart of the method for prognostic maintenance in semiconductor manufacturing equipments according to the present invention. -
FIG. 4 is a flowchart of the statistic classification model according to the present invention. -
FIG. 5 is a flowchart of the prescribed classification method according to the present invention. - Refer now to
FIG. 3 , wherein the present invention proposes a method for prognostic maintenance in semiconductor manufacturing equipments, and the method for prognostic maintenance in semiconductor manufacturing equipments comprising the following steps: - S100: collecting a plurality of raw data, and performing preprocesses on the plurality of raw data;
- S102: performing classification on the plurality of preprocessed raw data by means of a statistic classification model in order to generate a plurality of health indices;
- S104: performing classification on the plurality of health indices by a prescribed classification method so as to generate a plurality of health information;
- S106: using a regression analysis method to process the plurality of health information to generate a plurality of health reports.
- To facilitate those skilled in the art to understand and implement the present invention, herein the detailed descriptions illustrate technical details of the present invention. Initially, in-situ engineers use the Fault Detection and Classification (FDC) system to collect a plurality of raw data, wherein the collected raw data are the variation values detected in real-time on each wafer by the FDC system during semiconductor processes.
- Afterward, preprocess the plurality of raw data, which is directed to filter out meaningless null variation values existing in the plurality of raw data, and to generate detection values of normal pattern; and the plurality of raw data further consist of a plurality of historic data and a plurality of newly added data, in which the plurality of historic data indicate the data outputted by the semiconductor equipments under healthy condition in the past, and the plurality of newly added data represent the data outputted by the semiconductor equipment under unknown condition at current time.
- Next, use a statistic classification model to process the plurality of preprocessed raw data, which is simply the plurality of raw data after the said preprocess, so as to generate a plurality of health indices, wherein the statistic classification model refers to the Neural Network Model (NN Model), and the steps taken in such a statistic classification model comprise (also refer to
FIG. 4 ): - (A) Learning Phase:
- A100: simplifying the plurality of historic data; that is, performing classification on the plurality of historic data by a neural network classifier, acquiring a plurality of historic neural points;
- A102: processing the plurality of historic neural points, so as to generate a distribution configuration of the plurality of historic neural points according to the plurality of historic neural points, thus acquiring an elliptic distribution configuration of the plurality of historic neural points.
- (B) On-Line Monitoring Phase:
- B100: simplifying the plurality of newly added data; that is, performing classification on the plurality of newly added data by the neural network classifier, acquiring a plurality of newly added neural points;
- B102: processing the plurality of newly added neural points, so as to generate a distribution configuration of the plurality of newly added neural points according to the plurality of newly added neural points, and building the distribution configuration of the plurality of newly added neural points within the above-said elliptic distribution configuration.
- (C) Comparison Phase:
- C100: comparing the plurality of historic neural points with the plurality of newly added neural points based on the elliptic distribution configuration, thus generating a plurality of comparison values;
- C102: conjunctively processing the plurality of comparison values to generate a plurality of health indices.
- Due to high number of dimensions existing in the plurality of health indices, the significant complexity prevents direct usability thereof by in-situ engineers; accordingly, after acquisition of the plurality of health indices, it is necessary to use a prescribed classification method to perform classification on the plurality of health indices for dimensional reduction, thus generating a plurality of health information, wherein the said prescribed classification method is essentially the Principal Component Analysis (PCA), and the steps taken in the prescribed classification method comprise (also refer to
FIG. 5 ): - (A) performing a linear conversion operation on the plurality of health indices through the PCA; i.e. converting the plurality of health indices in an original coordinate system into a plurality of health indices in a new coordinate system, wherein such a new coordinate system has a plurality of new coordinate axes, and the plurality of new coordinate axes are respectively the first new axis, the second new axis, . . . , and the Nth new axis, wherein the first new axis being referred as the first principal component, second new axis referred as the second principal component, . . . , and Nth new axis referred as the Nth principal component; furthermore, each of the new axes is a linear combination of the original axes in the original coordinate system;
- (B) by such a new coordinate system, finding projection values of the plurality of health indices projected onto the plurality of new axes, acquiring a plurality of first principal component values over the first new axis (the first principal components), a plurality of second principal component values over the second new axis (the second principal components), . . . , and a plurality of Nth principal component values over the Nth new axis (the Nth principal components);
- (C) analyzing the plurality of first principal component values, plurality of second principal component values, . . . , and plurality of Nth principal component values based on a plurality of confidence indices built by in-situ engineers to acquire a plurality of principal component characteristic values, wherein the plurality of principal component characteristic values indicating the plurality of health indices, wherein the purpose of such confidence indices is intended to simplify the plurality of health indices through retaining lower-rank principal component values but ignoring higher-rank principal component values;
- (D) generating a plurality of health information according to the principal component characteristic values of the plurality of health indices.
- After acquisition of the plurality of health information, it further processes the plurality of health information by regression analysis to generate a plurality of health reports, wherein the employed regression analysis is the Partial Least Squares Discriminated Analysis (PLS-DA).
- Finally, the plurality of health reports are provided to in-situ engineers for assisting in-situ engineers in appreciating the health condition of the semiconductor equipments beforehand, such that in-situ engineers are capable of actively performing related repairs and maintenance thereon.
- Accordingly, the method of the present invention has the following advantages:
- 1. through the method of the present invention, in-situ engineers can appreciate in advance the health level of the semiconductor equipments, allowing to actively perform repairs or maintenance, avoiding subsequent damages to wafers which may cause reduction in wafer yield;
- 2. the method of the present invention uses simple classification operations, and data after such operation processes can provide in-situ engineers with information concerning health level of the semiconductor equipments;
- 3. it is still possible to retain original real-time information contents, without any operational losses due to processes which may lead to undesirable distortion in analysis results;
- 4. it saves significant time and manpower resources, facilitating performance enhancement in semiconductor equipment control and management;
- 5. it can predict as well as inform in-situ engineers of failure or breakdown in semiconductor equipments early before the occurrences thereof, allowing in-situ engineers to perform required repairs and maintenance on the semiconductor equipments under poor health condition, thereby extending lifespan of the semiconductor equipments.
- The aforementioned descriptions simply illustrate the preferred embodiments of the present invention, rather than being used to restrict the scope of the present invention to be legally protected; hence, all effectively equivalent changes or modifications made based on the disclosure of the present invention and appended drawings thereof are reasonably deemed to fall within the scope of the present invention delineated by the subsequent claims.
Claims (15)
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW97121198A | 2008-06-06 | ||
TW097121198A TW200951752A (en) | 2008-06-06 | 2008-06-06 | A method for prognostic maintenance in semiconductor manufacturing |
TW97121198 | 2008-06-06 |
Publications (2)
Publication Number | Publication Date |
---|---|
US20090306804A1 true US20090306804A1 (en) | 2009-12-10 |
US7904195B2 US7904195B2 (en) | 2011-03-08 |
Family
ID=40266146
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/243,370 Active 2029-07-31 US7904195B2 (en) | 2008-06-06 | 2008-10-01 | Method for prognostic maintenance in semiconductor manufacturing equipments |
Country Status (3)
Country | Link |
---|---|
US (1) | US7904195B2 (en) |
EP (1) | EP2131258A1 (en) |
TW (1) | TW200951752A (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100234978A1 (en) * | 2009-03-11 | 2010-09-16 | Inotera Memories, Inc. | Method for finding the correlation between the tool pm and the product yield |
CN105956364A (en) * | 2016-04-20 | 2016-09-21 | 云南中烟工业有限责任公司 | Tobacco leaf distinguishing grouping method based on characteristic chemical component |
CN109711453A (en) * | 2018-12-21 | 2019-05-03 | 广东工业大学 | A kind of equipment dynamical health state evaluating method based on multivariable |
US20190196458A1 (en) * | 2017-12-25 | 2019-06-27 | Marketech International Corp. | Method for selecting leading associated parameter and method for combining critical parameter and leading associated parameter for equipment prognostics and health management |
WO2020044238A1 (en) * | 2018-08-29 | 2020-03-05 | Cerebras Systems Inc. | Processor element redundancy for accelerated deep learning |
US10657438B2 (en) | 2017-04-17 | 2020-05-19 | Cerebras Systems Inc. | Backpressure for accelerated deep learning |
US10699189B2 (en) | 2017-02-23 | 2020-06-30 | Cerebras Systems Inc. | Accelerated deep learning |
US10726329B2 (en) | 2017-04-17 | 2020-07-28 | Cerebras Systems Inc. | Data structure descriptors for deep learning acceleration |
CN114001771A (en) * | 2020-07-28 | 2022-02-01 | 通用电气公司 | System and method for diagnosing an additive manufacturing device using a physically-assisted machine learning model |
US11321087B2 (en) | 2018-08-29 | 2022-05-03 | Cerebras Systems Inc. | ISA enhancements for accelerated deep learning |
US11328207B2 (en) | 2018-08-28 | 2022-05-10 | Cerebras Systems Inc. | Scaled compute fabric for accelerated deep learning |
US11488004B2 (en) | 2017-04-17 | 2022-11-01 | Cerebras Systems Inc. | Neuron smearing for accelerated deep learning |
Families Citing this family (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110087387A1 (en) * | 2009-10-12 | 2011-04-14 | The Boeing Company | Platform Health Monitoring System |
US8914149B2 (en) | 2009-10-12 | 2014-12-16 | The Boeing Company | Platform health monitoring system |
US8572009B2 (en) | 2011-08-16 | 2013-10-29 | The Boeing Company | Evaluating the health status of a system using groups of vibration data including images of the vibrations of the system |
EP2709041B1 (en) | 2012-09-17 | 2014-11-12 | Nxp B.V. | Method and System for Monitoring the State of Health of an Electronic Data Carrier |
TWI570587B (en) * | 2015-12-07 | 2017-02-11 | 財團法人工業技術研究院 | System and method for predicting remaining useful life of component of semiconductor equipment |
CN106529062B (en) * | 2016-11-20 | 2019-10-11 | 重庆交通大学 | A kind of bridge structure health diagnostic method based on deep learning |
CN110083849A (en) * | 2018-01-25 | 2019-08-02 | 中芯国际集成电路制造(上海)有限公司 | Flexible measurement method, computer and the computer-readable medium of semiconductor manufacturing facility |
WO2020055555A1 (en) * | 2018-09-12 | 2020-03-19 | Applied Materials, Inc. | Deep auto-encoder for equipment health monitoring and fault detection in semiconductor and display process equipment tools |
US11062233B2 (en) | 2018-12-21 | 2021-07-13 | The Nielsen Company (Us), Llc | Methods and apparatus to analyze performance of watermark encoding devices |
CN116468419B (en) * | 2023-03-15 | 2024-07-02 | 成都地铁运营有限公司 | Rail transit big data operation and maintenance decision analysis method, device and storage medium |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5761383A (en) * | 1995-04-27 | 1998-06-02 | Northrop Grumman Corporation | Adaptive filtering neural network classifier |
US6519575B1 (en) * | 2000-04-24 | 2003-02-11 | General Electric Company | System and method for classifying unknown data patterns in multi-variate feature space |
US20060129257A1 (en) * | 2004-12-13 | 2006-06-15 | Taiwan Semiconductor Manufacturing Co., Ltd. | Novel method and apparatus for integrating fault detection and real-time virtual metrology in an advanced process control framework |
US20070067678A1 (en) * | 2005-07-11 | 2007-03-22 | Martin Hosek | Intelligent condition-monitoring and fault diagnostic system for predictive maintenance |
US7242995B1 (en) * | 2004-10-25 | 2007-07-10 | Rockwell Automation Technologies, Inc. | E-manufacturing in semiconductor and microelectronics processes |
US20080082197A1 (en) * | 2006-09-22 | 2008-04-03 | Jerome Henri Noel Lacaille | Global predictive monitoring system for a manufacturing facility |
US20080141072A1 (en) * | 2006-09-21 | 2008-06-12 | Impact Technologies, Llc | Systems and methods for predicting failure of electronic systems and assessing level of degradation and remaining useful life |
US7401066B2 (en) * | 2002-03-21 | 2008-07-15 | Applied Materials, Inc. | Correlation of end-of-line data mining with process tool data mining |
US20080312783A1 (en) * | 2007-06-12 | 2008-12-18 | The Boeing Company | Systems and Methods for Health Monitoring of Complex Systems |
US7487059B2 (en) * | 2007-06-21 | 2009-02-03 | The Boeing Company | Transducer health diagnostics for structural health monitoring (SHM) systems |
US7536277B2 (en) * | 2004-04-21 | 2009-05-19 | University Of Connecticut | Intelligent model-based diagnostics for system monitoring, diagnosis and maintenance |
US7581434B1 (en) * | 2003-09-25 | 2009-09-01 | Rockwell Automation Technologies, Inc. | Intelligent fluid sensor for machinery diagnostics, prognostics, and control |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6442445B1 (en) * | 1999-03-19 | 2002-08-27 | International Business Machines Corporation, | User configurable multivariate time series reduction tool control method |
WO2005054968A1 (en) * | 2003-11-26 | 2005-06-16 | Tokyo Electron Limited | Intelligent system for detection of process status, process fault and preventive maintenance |
US7321809B2 (en) | 2003-12-30 | 2008-01-22 | The Boeing Company | Methods and systems for analyzing engine unbalance conditions |
US7477960B2 (en) * | 2005-02-16 | 2009-01-13 | Tokyo Electron Limited | Fault detection and classification (FDC) using a run-to-run controller |
-
2008
- 2008-06-06 TW TW097121198A patent/TW200951752A/en unknown
- 2008-10-01 US US12/243,370 patent/US7904195B2/en active Active
- 2008-10-20 EP EP08167035A patent/EP2131258A1/en not_active Withdrawn
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5761383A (en) * | 1995-04-27 | 1998-06-02 | Northrop Grumman Corporation | Adaptive filtering neural network classifier |
US6519575B1 (en) * | 2000-04-24 | 2003-02-11 | General Electric Company | System and method for classifying unknown data patterns in multi-variate feature space |
US7401066B2 (en) * | 2002-03-21 | 2008-07-15 | Applied Materials, Inc. | Correlation of end-of-line data mining with process tool data mining |
US7581434B1 (en) * | 2003-09-25 | 2009-09-01 | Rockwell Automation Technologies, Inc. | Intelligent fluid sensor for machinery diagnostics, prognostics, and control |
US7536277B2 (en) * | 2004-04-21 | 2009-05-19 | University Of Connecticut | Intelligent model-based diagnostics for system monitoring, diagnosis and maintenance |
US7242995B1 (en) * | 2004-10-25 | 2007-07-10 | Rockwell Automation Technologies, Inc. | E-manufacturing in semiconductor and microelectronics processes |
US20060129257A1 (en) * | 2004-12-13 | 2006-06-15 | Taiwan Semiconductor Manufacturing Co., Ltd. | Novel method and apparatus for integrating fault detection and real-time virtual metrology in an advanced process control framework |
US20070067678A1 (en) * | 2005-07-11 | 2007-03-22 | Martin Hosek | Intelligent condition-monitoring and fault diagnostic system for predictive maintenance |
US20080141072A1 (en) * | 2006-09-21 | 2008-06-12 | Impact Technologies, Llc | Systems and methods for predicting failure of electronic systems and assessing level of degradation and remaining useful life |
US20080082197A1 (en) * | 2006-09-22 | 2008-04-03 | Jerome Henri Noel Lacaille | Global predictive monitoring system for a manufacturing facility |
US20080312783A1 (en) * | 2007-06-12 | 2008-12-18 | The Boeing Company | Systems and Methods for Health Monitoring of Complex Systems |
US7487059B2 (en) * | 2007-06-21 | 2009-02-03 | The Boeing Company | Transducer health diagnostics for structural health monitoring (SHM) systems |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100234978A1 (en) * | 2009-03-11 | 2010-09-16 | Inotera Memories, Inc. | Method for finding the correlation between the tool pm and the product yield |
US8032248B2 (en) * | 2009-03-11 | 2011-10-04 | Inotera Memories, Inc. | Method for finding the correlation between the tool PM and the product yield |
CN105956364A (en) * | 2016-04-20 | 2016-09-21 | 云南中烟工业有限责任公司 | Tobacco leaf distinguishing grouping method based on characteristic chemical component |
US11934945B2 (en) | 2017-02-23 | 2024-03-19 | Cerebras Systems Inc. | Accelerated deep learning |
US10699189B2 (en) | 2017-02-23 | 2020-06-30 | Cerebras Systems Inc. | Accelerated deep learning |
US11232348B2 (en) | 2017-04-17 | 2022-01-25 | Cerebras Systems Inc. | Data structure descriptors for deep learning acceleration |
US10657438B2 (en) | 2017-04-17 | 2020-05-19 | Cerebras Systems Inc. | Backpressure for accelerated deep learning |
US10726329B2 (en) | 2017-04-17 | 2020-07-28 | Cerebras Systems Inc. | Data structure descriptors for deep learning acceleration |
US10762418B2 (en) | 2017-04-17 | 2020-09-01 | Cerebras Systems Inc. | Control wavelet for accelerated deep learning |
US11062200B2 (en) | 2017-04-17 | 2021-07-13 | Cerebras Systems Inc. | Task synchronization for accelerated deep learning |
US11157806B2 (en) | 2017-04-17 | 2021-10-26 | Cerebras Systems Inc. | Task activating for accelerated deep learning |
US11232347B2 (en) | 2017-04-17 | 2022-01-25 | Cerebras Systems Inc. | Fabric vectors for deep learning acceleration |
US11488004B2 (en) | 2017-04-17 | 2022-11-01 | Cerebras Systems Inc. | Neuron smearing for accelerated deep learning |
US11475282B2 (en) | 2017-04-17 | 2022-10-18 | Cerebras Systems Inc. | Microthreading for accelerated deep learning |
US20190196458A1 (en) * | 2017-12-25 | 2019-06-27 | Marketech International Corp. | Method for selecting leading associated parameter and method for combining critical parameter and leading associated parameter for equipment prognostics and health management |
US11328207B2 (en) | 2018-08-28 | 2022-05-10 | Cerebras Systems Inc. | Scaled compute fabric for accelerated deep learning |
WO2020044238A1 (en) * | 2018-08-29 | 2020-03-05 | Cerebras Systems Inc. | Processor element redundancy for accelerated deep learning |
US11328208B2 (en) | 2018-08-29 | 2022-05-10 | Cerebras Systems Inc. | Processor element redundancy for accelerated deep learning |
US11321087B2 (en) | 2018-08-29 | 2022-05-03 | Cerebras Systems Inc. | ISA enhancements for accelerated deep learning |
CN109711453A (en) * | 2018-12-21 | 2019-05-03 | 广东工业大学 | A kind of equipment dynamical health state evaluating method based on multivariable |
EP3945387A1 (en) * | 2020-07-28 | 2022-02-02 | General Electric Company | Systems, and methods for diagnosing an additive manufacturing device using a physics assisted machine learning model |
CN114001771A (en) * | 2020-07-28 | 2022-02-01 | 通用电气公司 | System and method for diagnosing an additive manufacturing device using a physically-assisted machine learning model |
Also Published As
Publication number | Publication date |
---|---|
TW200951752A (en) | 2009-12-16 |
US7904195B2 (en) | 2011-03-08 |
EP2131258A1 (en) | 2009-12-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7904195B2 (en) | Method for prognostic maintenance in semiconductor manufacturing equipments | |
US20210241544A1 (en) | Platform for analyzing health of heavy electric machine and analysis method using the same | |
CN1186476C (en) | Device and method for detecting and preventing arcing in RF plasma systems | |
US20060241802A1 (en) | Real-time management systems and methods for manufacturing management and yield rate analysis integration | |
US8594823B2 (en) | Scanner performance comparison and matching using design and defect data | |
KR20010029984A (en) | Real time defect source identification | |
JP2012532425A (en) | Automatic detection and classification of faults in plasma processing systems and methods | |
WO2007125941A1 (en) | Method and system for classifying defect distribution, method and system for specifying causative equipment, computer program and recording medium | |
KR20150140358A (en) | System and method for the automatic determination of critical parametric electrical test parameters for inline yield monitoring | |
CN109141625B (en) | Online state monitoring method for ball screw pair | |
US8649990B2 (en) | Method for detecting variance in semiconductor processes | |
CN117808456A (en) | Equipment fault early warning method and device based on intelligent operation management | |
CN114740343B (en) | Real-time detection system for circuit breaker | |
US8095895B2 (en) | Method for defect diagnosis and management | |
JP2011054804A (en) | Method and system for management of semiconductor manufacturing device | |
US20130138239A1 (en) | Semiconductor yield management system | |
Gleason et al. | Rapid yield learning through optical defect and electrical test analysis | |
JP2002110493A (en) | Method and apparatus for extracting failure in machining process | |
Weber et al. | Quantifying the value of ownership of yield analysis technologies | |
US20100010763A1 (en) | Method for detecting variance in semiconductor processes | |
Weber et al. | A yield management strategy for semiconductor manufacturing based on information theory | |
JP3324447B2 (en) | Estimation method of yield inhibition factor | |
JP5336947B2 (en) | Batch type manufacturing process monitoring method and monitoring apparatus | |
JP3916771B2 (en) | Manufacturing method of semiconductor device | |
US20050075835A1 (en) | System and method of real-time statistical bin control |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: INOTERA MEMORIES, INC., TAIWAN Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:CHAO, CHUNG-PEI;CHEN, CHIN-LONG;REEL/FRAME:021624/0089 Effective date: 20080603 |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
FPAY | Fee payment |
Year of fee payment: 4 |
|
AS | Assignment |
Owner name: MORGAN STANLEY SENIOR FUNDING, INC., MARYLAND Free format text: SUPPLEMENT NO. 3 TO PATENT SECURITY AGREEMENT;ASSIGNOR:MICRON TECHNOLOGY, INC.;REEL/FRAME:041675/0105 Effective date: 20170124 |
|
AS | Assignment |
Owner name: MICRON TECHNOLOGY, INC., IDAHO Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:INOTERA MEMORIES, INC.;REEL/FRAME:041820/0815 Effective date: 20170222 |
|
FEPP | Fee payment procedure |
Free format text: PAYOR NUMBER ASSIGNED (ORIGINAL EVENT CODE: ASPN) |
|
AS | Assignment |
Owner name: JPMORGAN CHASE BANK, N.A., AS COLLATERAL AGENT, ILLINOIS Free format text: SECURITY INTEREST;ASSIGNORS:MICRON TECHNOLOGY, INC.;MICRON SEMICONDUCTOR PRODUCTS, INC.;REEL/FRAME:047540/0001 Effective date: 20180703 Owner name: JPMORGAN CHASE BANK, N.A., AS COLLATERAL AGENT, IL Free format text: SECURITY INTEREST;ASSIGNORS:MICRON TECHNOLOGY, INC.;MICRON SEMICONDUCTOR PRODUCTS, INC.;REEL/FRAME:047540/0001 Effective date: 20180703 |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 8TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1552); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY Year of fee payment: 8 |
|
AS | Assignment |
Owner name: MICRON TECHNOLOGY, INC., IDAHO Free format text: RELEASE BY SECURED PARTY;ASSIGNOR:MORGAN STANLEY SENIOR FUNDING, INC., AS COLLATERAL AGENT;REEL/FRAME:050695/0825 Effective date: 20190731 |
|
AS | Assignment |
Owner name: MICRON SEMICONDUCTOR PRODUCTS, INC., IDAHO Free format text: RELEASE BY SECURED PARTY;ASSIGNOR:JPMORGAN CHASE BANK, N.A., AS COLLATERAL AGENT;REEL/FRAME:051028/0001 Effective date: 20190731 Owner name: MICRON TECHNOLOGY, INC., IDAHO Free format text: RELEASE BY SECURED PARTY;ASSIGNOR:JPMORGAN CHASE BANK, N.A., AS COLLATERAL AGENT;REEL/FRAME:051028/0001 Effective date: 20190731 |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 12TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1553); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY Year of fee payment: 12 |